A RAGFlow Model Context Protocol (MCP) server is designed as an independent component to complement the RAGFlow server. Note that an MCP server must operate alongside a properly functioning RAGFlow server.
An MCP server can start up in either self-host mode (default) or host mode:
- **Self-host mode**:
When launching an MCP server in self-host mode, you must provide an API key to authenticate the MCP server with the RAGFlow server. In this mode, the MCP server can access *only* the datasets (knowledge bases) of a specified tenant on the RAGFlow server.
- **Host mode**:
In host mode, each MCP client can access their own knowledge bases on the RAGFlow server. However, each client request must include a valid API key to authenticate the client with the RAGFlow server.
Once a connection is established, an MCP server communicates with its client in MCP HTTP+SSE (Server-Sent Events) mode, unidirectionally pushing responses from the RAGFlow server to its client in real time.
## Prerequisites
1. Ensure RAGFlow is upgraded to v0.18.0 or later.
2. Have your RAGFlow API key ready. See [Acquire a RAGFlow API key](./acquire_ragflow_api_key.md).
:::tip INFO
If you wish to try out our MCP server without upgrading RAGFlow, community contributor **yiminghub2024** 👏 shares their recommended steps [here](#launch-an-mcp-server-without-upgrading-ragflow).
ragflow-server | 2025-04-18 15:41:34,501 INFO 32 TaskExecutor: RAGFlow version: v0.18.0-285-gb2c299fa full
ragflow-server | 2025-04-18 15:41:34,501 INFO 32 Use Elasticsearch http://es01:9200 as the doc engine.
...
```
#### Launch an MCP server without upgrading RAGFlow
:::tip KUDOS-TO
This section is contributed by our community contributor **yiminghub2024**. 👏
:::
1. Prepare all MCP-specific files and directories.
i. Copy the [mcp/](https://github.com/infiniflow/ragflow/tree/main/mcp) directory to your local working directory.
ii. Copy [docker/docker-compose.yml](https://github.com/infiniflow/ragflow/blob/main/docker/docker-compose.yml) locally.
iii. Copy [docker/entrypoint.sh](https://github.com/infiniflow/ragflow/blob/main/docker/entrypoint.sh) locally.
iv. Install required dependencies using `uv`:
- Run `uv add mcp` or
- Copy pyproject.toml and run `uv sync --python 3.10 --all-extras`.
2. Edit **docker-compose.yml** to enable MCP (disable by default).
3. Launch the MCP server:
```bash
docker compose -f docker-compose.yml up -d`
```
### Check MCP server status
Run the following to check the logs the RAGFlow server and the MCP server:
```bash
docker logs ragflow-server
```
## MCP client example
We provide a *prototype* MCP client example for testing [here](https://github.com/infiniflow/ragflow/blob/main/mcp/client/client.py).
:::danger IMPORTANT
If your MCP server is running in host mode, include your acquired API key in your client's `headers` as shown below:
```python
async with sse_client("http://localhost:9382/sse", headers={"api_key": "YOUR_KEY_HERE"}) as streams:
# Rest of your code...
```
:::
## API
The MCP server currently offers an API to assist users in searching for relevant information powered by RAGFlow DeepDoc technology:
- **retrieve**: Fetches relevant chunks from specified `dataset_ids` and optional `document_ids` using the RAGFlow retrieve interface, based on a given question. Details of all available datasets, namely, `id` and `description`, are provided within the tool description for each individual dataset.
## Security considerations
As MCP technology is still at early stage and no official best practices for authentication or authorization have been established, RAGFlow currently uses [API key](./acquire_ragflow_api_key.md) to validate identity for the operations described earlier. However, in public environments, this makeshift solution could expose your MCP server to potential network attacks. Therefore, when running a local SSE server, it is recommended to bind only to localhost (`127.0.0.1`) rather than to all interfaces (`0.0.0.0`).
For further guidance, see the [official MCP documentation](https://modelcontextprotocol.io/docs/concepts/transports#security-considerations).
